From 6668ed271eaefaa63e686bdfbedaeb7b8e492722 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Sep 2026 10:43:19 +0200 Subject: selftests/bpf: Reject graph kptr use after RCU unlock Add a sleepable verifier test that loads a graph-node local kptr in an explicit RCU read-side critical section, then passes its node to bpf_rbtree_remove() after the section ends. Before the verifier fix, the stale NON_OWN_REF flag makes the node look like a live borrowed reference and the program is accepted. After the fix, the pointer is demoted without NON_OWN_REF and the graph kfunc argument is rejected. Also exercise a graph kptr loaded while a spin lock provides implicit RCU protection. The pointer must be invalidated when the lock is released, which guards the required ordering between non-owning-reference invalidation and RCU demotion. Update the existing fault-protected load test state description. The post-unlock pointer no longer carries NON_OWN_REF, but remains readable because the load is rewritten to use BPF_PROBE_MEM. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260904084325.52250-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- io_uring/wait.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 io_uring/wait.h (limited to 'io_uring/wait.h') diff --git a/io_uring/wait.h b/io_uring/wait.h new file mode 100644 index 000000000..b7b9c46b1 --- /dev/null +++ b/io_uring/wait.h @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef IOU_WAIT_H +#define IOU_WAIT_H + +#include + +/* + * ->cq_wait_nr is armed with the number of lazy task_work adds the waiter + * still needs, and counted down by the add side, with the add reaching zero + * issuing the (single) wake up for this wait cycle. Zero and below means no + * wake up is to be issued: IO_CQ_WAKE_INIT when no task is waiting (also + * what a forced wake up resets it to when claiming one), zero once the + * countdown has fired. + */ +#define IO_CQ_WAKE_INIT (-1) + +struct ext_arg { + size_t argsz; + struct timespec64 ts; + const sigset_t __user *sig; + ktime_t min_time; + bool ts_set; + bool iowait; +}; + +int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, + struct ext_arg *ext_arg); +int io_run_task_work_sig(struct io_ring_ctx *ctx); +void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx); +void io_cqring_overflow_flush_locked(struct io_ring_ctx *ctx); + +static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = io_get_rings(ctx); + return ctx->cached_cq_tail - READ_ONCE(rings->cq.head); +} + +static inline unsigned int __io_cqring_events_user(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = io_get_rings(ctx); + + return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head); +} + +/* + * Reads the tail/head of the CQ ring while providing an acquire ordering, + * see comment at top of io_uring.c. + */ +static inline unsigned io_cqring_events(struct io_ring_ctx *ctx) +{ + smp_rmb(); + return __io_cqring_events(ctx); +} + +#endif -- cgit v1.3.1